Update README.md

README.md

@@ -1,199 +1,224 @@
 ---
+language:
+- multilingual
+license: apache-2.0
 library_name: transformers
-tags: []
+datasets:
+- lamm-mit/Cephalo-Bioinspired-Mechanics-Materials
+- lamm-mit/Cephalo-Wikipedia-Materials
+tags:
+- nlp
+- code
+- vision
+- chemistry
+- engineering
+- biology
+- bio-inspired
+- text-generation-inference
+- materials science
+pipeline_tag: image-text-to-text
+inference:
+  parameters:
+    temperature: 0.3
+widget:
+- messages:
+  - role: user
+    content: <|image_1|>Can you describe what you see in the image?
 ---
+## Model Summary
 
-# Model Card for Model ID
+Cephalo is a series of multimodal materials science focused vision large language models (V-LLMs) designed to integrate visual and linguistic data for advanced understanding and interaction in human-AI or multi-agent AI frameworks. 
 
-<!-- Provide a quick summary of what the model is/does. -->
+A novel aspect of Cephalo's development is the innovative dataset generation method. The extraction process employs advanced algorithms to accurately detect and separate images and their corresponding textual descriptions from complex PDF documents. It involves extracting images and captions from PDFs to create well-reasoned image-text pairs, utilizing large language models (LLMs) for natural language processing. These image-text pairs are then refined and validated through LLM-based NLP processing, ensuring high-quality and contextually relevant data for training. 
 
+Cephalo can interpret complex visual scenes and generating contextually accurate language descriptions and answer queries. 
 
+The model is developed to process diverse inputs, including images and text, facilitating a broad range of applications such as image captioning, visual question answering, and multimodal content generation. The architecture combines a vision encoder model and an autoregressive transformer to process complex natural language understanding. 
 
-## Model Details
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/623ce1c6b66fedf374859fe7/kl5GWBP9WS0D4uwd1t3S7.png)
 
-### Model Description
+Cephalo provides a robust framework for multimodal interaction and understanding, including the development of complex generative pipelines to create 2D and 3D renderings of material microstructures as input for additive manufacturing methods.
 
-<!-- Provide a longer summary of what this model is. -->
+This version of Cephalo, lamm-mit/Cephalo-Phi-3-MoE-vision-128k-3x4b-beta, is a Mixture-of-Expert model based on the Phi-3-Vision-128K-Instruct model. 
 
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+###
 
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
+```python
+from transformers import AutoModelForCausalLM, AutoProcessor,AutoConfig  
 
-### Model Sources [optional]
+def count_parameters(model):
+    total_params = sum(p.numel() for p in model.parameters())
+    trainable_params = sum(p.numel() for p in model.parameters() if p.requires_grad)
+    return total_params/1e9, trainable_params/1e9
 
-<!-- Provide the basic links for the model. -->
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
+model_name_moe = "lamm-mit/Cephalo-Phi-3-MoE-vision-128k-3x4b-beta"
 
-## Uses
+processor = AutoProcessor.from_pretrained(model_name_moe, trust_remote_code=True) 
+moe_model = AutoModelForCausalLM.from_pretrained(
+    model_name_moe,
+    trust_remote_code=True,  torch_dtype=torch.bfloat16,    
+).to(device)
+count_parameters(moe_model)
+```
 
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+## Make a Phi-3-V-MoE model from several pre-trained models
+```python
+from Phi_3V_MoE.moe_phi3_v import Phi3VForCausalLMMoE, Phi3VForCausalLMMoEConfig
 
-### Direct Use
 
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 
-[More Information Needed]
+model_name_1 = f"lamm-mit/Cephalo-Phi-3-vision-128k-4b-beta"
+model_1 = AutoModelForCausalLM.from_pretrained(
+    model_name_1,
+    trust_remote_code=True,  torch_dtype=torch.bfloat16, 
+    
+).to(device)
 
-### Downstream Use [optional]
+model_name_2 = f"microsoft/Phi-3-vision-128k-instruct"
+model_2 = AutoModelForCausalLM.from_pretrained(
+    model_name_2,
+    trust_remote_code=True,  torch_dtype=torch.bfloat16, 
+    
+).to(device)
 
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+model_name_3 = f"lamm-mit/Cephalo-Phi-3-vision-128k-4b-alpha"
 
-[More Information Needed]
+model_3 = AutoModelForCausalLM.from_pretrained(
+    model_name_3,
+    trust_remote_code=True,  torch_dtype=torch.bfloat16, 
+    
+).to(device)
 
-### Out-of-Scope Use
+dtype = torch.bfloat16  # Desired dtype for new layers
 
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+# Initialize the models
+base_model = copy.deepcopy(model_2)  # Your base model
+expert_models = [model_1, model_2,  model_3  ]  # List of expert models
+ 
+# Load a processor (e.g. from base model)
+processor = AutoProcessor.from_pretrained(model_name_2, trust_remote_code=True) 
 
-[More Information Needed]
+# Create the config
+config =  AutoConfig.from_pretrained(model_name_2, trust_remote_code=True)
 
-## Bias, Risks, and Limitations
+# Create the MoE model
+moe_config = Phi3VForCausalLMMoEConfig(config=config, k=1, num_expert_models=len (expert_models))
+moe_model = Phi3VForCausalLMMoE(moe_config, base_model, expert_models,  layer_dtype = dtype).to(device)
 
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+count_parameters(expert_models[0]),count_parameters(moe_model)
+```
 
-[More Information Needed]
+####################
 
-### Recommendations
 
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+### Chat Format
 
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+Given the nature of the training data, the Cephalo-Phi-3-vision-128k-4b-beta model is best suited for a single image input wih prompts using the chat format as follows. 
+You can provide the prompt as a single image with a generic template as follow:
+```markdown
+<|user|>\n<|image_1|>\n{prompt}<|end|>\n<|assistant|>\n 
+```
 
-## How to Get Started with the Model
+where the model generates the text after `<|assistant|>` . For multi-turn conversations, the prompt should be formatted as follows:
 
-Use the code below to get started with the model.
+```markdown
+<|user|>\n<|image_1|>\n{prompt_1}<|end|>\n<|assistant|>\n{response_1}<|end|>\n<|user|>\n{prompt_2}<|end|>\n<|assistant|>\n 
+```
 
-[More Information Needed]
+### Sample inference code
 
-## Training Details
+This code snippets show how to get quickly started on a GPU:
 
-### Training Data
+```python
+from PIL import Image 
+import requests 
+from transformers import AutoModelForCausalLM 
+from transformers import AutoProcessor 
 
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+model_id = "lamm-mit/Cephalo-Phi-3-vision-128k-4b-beta" 
 
-[More Information Needed]
+model = AutoModelForCausalLM.from_pretrained(model_id, device_map="cuda", trust_remote_code=True, torch_dtype="auto")
 
-### Training Procedure
+processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True) 
 
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+question = "What is shown in this image, and what is the relevance for materials design? Include a discussion of multi-agent AI."
 
-#### Preprocessing [optional]
+messages = [ 
+    {"role": "user", "content": f"<|image_1|>\n{question}"}, 
+    ] 
 
-[More Information Needed]
+url = "https://d2r55xnwy6nx47.cloudfront.net/uploads/2018/02/Ants_Lede1300.jpg" 
 
+image = Image.open(requests.get(url, stream=True).raw) 
 
-#### Training Hyperparameters
+prompt = processor.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
 
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+inputs = processor(prompt, [image], return_tensors="pt").to("cuda:0") 
 
-#### Speeds, Sizes, Times [optional]
+generation_args = { 
+                    "max_new_tokens": 512, 
+                    "temperature": 0.1, 
+                    "do_sample": True, 
+                    "stop_strings": ['<|end|>',
+                                     '<|endoftext|>'],
+                    "tokenizer": processor.tokenizer,
+                  } 
 
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+generate_ids = model.generate(**inputs, eos_token_id=processor.tokenizer.eos_token_id, **generation_args) 
 
-[More Information Needed]
+# remove input tokens 
+generate_ids = generate_ids[:, inputs['input_ids'].shape[1]:]
+response = processor.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0] 
 
-## Evaluation
+print(response) 
+```
+Sample output:
 
-<!-- This section describes the evaluation protocols and provides the results. -->
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/623ce1c6b66fedf374859fe7/5n6oRNHrfwHkBX0QertZp.png)
+<small>Image by [Vaishakh Manohar](https://www.quantamagazine.org/the-simple-algorithm-that-ants-use-to-build-bridges-20180226/)</small>
 
-### Testing Data, Factors & Metrics
+<pre style="white-space: pre-wrap;">
+The image shows a group of red ants (Solenopsis invicta) climbing over a vertical wooden post. The ants are using their long legs and antennae to navigate the rough surface of the wood, demonstrating their ability to adapt to different materials and environments. This behavior is relevant for materials design because it highlights the importance of considering the interactions between materials and living organisms, such as ants, when designing new materials.
 
-#### Testing Data
+Multi-agent AI (Artificial Intelligence) is a field of study that focuses on the development of AI systems that can work together with other AI systems to achieve a common goal. In the context of this image, multi-agent AI could be used to design materials that are more compatible with the natural behaviors of living organisms, such as ants, and that can adapt to different environments and conditions.
 
-<!-- This should link to a Dataset Card if possible. -->
+By studying the behavior of ants and other living organisms, researchers can gain insights into how materials can be designed to better interact with these organisms and to better mimic their natural behaviors. This can lead to the development of new materials that are more sustainable, efficient, and effective in a variety of applications.
 
-[More Information Needed]
+In summary, the image of red ants climbing over a wooden post highlights the importance of considering the interactions between materials and living organisms when designing new materials, and the potential of multi-agent AI to help achieve this goal.
+</pre>
 
-#### Factors
 
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+## Dataset generation
 
-[More Information Needed]
+The schematic below shows a visualization of the approach to generate datasets for training the vision model. The extraction process employs advanced algorithms to accurately detect and separate images and their corresponding textual descriptions from complex PDF documents. It involves extracting images and captions from PDFs to create well-reasoned image-text pairs, utilizing large language models (LLMs) for natural language processing. These image-text pairs are then refined and validated through LLM-based NLP processing, ensuring high-quality and contextually relevant data for training.
 
-#### Metrics
+The image below shows reproductions of two representative pages of the scientific article (here, Spivak, Buehler, et al., 2011), and how they are used to extract visual scientific data for training the Cephalo model.
 
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/623ce1c6b66fedf374859fe7/qHURSBRWEDgHy4o56escN.png)
 
-[More Information Needed]
 
-### Results
+## Example applications
 
-[More Information Needed]
+The paper provides detailed examples and use cases. Here is a visual of a pipeline that consists of 1) analysis of an image provided to Cephalo-Phi-3-vision-128k-4b-beta, 2) generation of an image generation fromt, and 3) generation of a new image using Stable Diffusion XL Turbo.
 
-#### Summary
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/623ce1c6b66fedf374859fe7/3VvHK_c9eJolQvfOrhiBw.png)
 
+A similar mechanism can be employed to generate 3D models:
 
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/623ce1c6b66fedf374859fe7/6ZsvCZ3x3TGvugly44MMI.png)
 
-## Model Examination [optional]
+## Citation
 
-<!-- Relevant interpretability work for the model goes here -->
+Please cite as:
 
-[More Information Needed]
-
-## Environmental Impact
-
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-
-## Technical Specifications [optional]
-
-### Model Architecture and Objective
-
-[More Information Needed]
-
-### Compute Infrastructure
-
-[More Information Needed]
-
-#### Hardware
-
-[More Information Needed]
-
-#### Software
-
-[More Information Needed]
-
-## Citation [optional]
-
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-
-**BibTeX:**
-
-[More Information Needed]
-
-**APA:**
-
-[More Information Needed]
-
-## Glossary [optional]
-
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-
-[More Information Needed]
-
-## More Information [optional]
-
-[More Information Needed]
-
-## Model Card Authors [optional]
-
-[More Information Needed]
-
-## Model Card Contact
-
-[More Information Needed]
+```bibtex
+@article{Buehler_Cephalo_2024,
+  title={Cephalo: Multi-Modal Vision-Language Models for Bio-Inspired Materials Analysis and Design},
+  author={Markus J. Buehler},
+  journal={arXiv preprint arXiv:2405.19076},
+  year={2024}
+}
+```